想要讓電腦了解一部電影的內容，並不是一件容易的事，因為在電影中可能發生的事件實在太過廣泛。既然這個目標並不容易達成，我們可以先實驗在電影中的一些低階視覺特徵會如何影響一部電影。基於一些已經被提出過的低階視覺特徵，我們提出了一個架構用電影的低階視覺特徵將電影類型分類。我們主要的研究題材是電影的預告片。一部電影的預告片通常會強調電影的主題，因此提供了適當的資訊來做電影分類，另一方面，預告片的取得也比一部完整的電影來的容易取得。在我們的方法中，我們將電影分為三大種類型：動作片，劇情片，恐怖片。藉由電影的一些原則，四種可計算的特徵( 平均鏡頭長度，色彩豐富度，運動量和明亮度) 被拿來分析這些特徵是否適合用來分類電影。在本篇論文中，我們另外提出了一項特徵，稱為視覺效果，用來區分劇情類或非劇情類影片。
本篇論文首先探討目前處理視訊的基本知識和方法，而論文的重點在於分析可用來分類的特徵。對任何一種分類問題而言，具有鑑別性的特徵才是最為重要的關鍵。在分析這些特徵之後，最後決定用分類樹與類神經網路的方式來對電影作分類。我們的方法也能夠被用到其他潛在的應用，以最少人力的幫助下建構及更新視訊資料庫，電腦對電影場景的認知，網路上的影片瀏覽及搜尋。

It is hard to achieve the goal that making computer understand a film content, because there are too many events may happen in a film. Since the difficult the film content in computer understanding, we first experiment how the low level visual features can affect a film. Based on some low level visual features have been proposed, we presents a framework for the classification of feature films into genres in this thesis. Our current domain of study is the movie preview. A film preview often emphasizes the theme of a film and hence provides suitable information for classification, on the other hand, a preview is more easy to get than a whole movie. In our approach, we classify movies into three broad categories: Action, Dramas,
or thriller films. In our experiment, four computable video features (average shot length, color variance, motion content and lighting key) are analysis that how well these features for classify films into genres. On the other hand, we proposed another features called visual effect to distinguish drama or non-drama films. Classification Tree and Neural network are used after analysis of these low level visual features, with the features distribution. After our experiment, we found that our approach can also be broadened for other potential applications including
the building and updating of video databases with minimal human intervention, scene understanding, browsing and retrieval of videos on the Internet and video libraries.

[1] G. Rafae and E. Richard, Digital Image Processing, 2 ed, Prentice Hall, 2002.
[2] \Wikipedia," Available: http://en.wikipedia.org/wiki/.
[3] D. Li and H. Q. Lu, "Shot detection with multi-measures," in Proc. of the 7th IEEE Int. Conf. on Electronics, Circuits and Systems, vol. 1, pp. 537-540, 2000.
[4] Z. Rasheed, Y. Sheikn, and M. Shah, "On the use of computable features for Film classification," IEEE Tran. on Circuits and System for Video Technology, vol. 15, pp. 52-63, 2005.
[5] Y. Wang, J. Ostermann, and Y. Q. Zhang, Video Processing And Communication, Prentice Hall, 2001.
[6] M. J. Pickering and S. Ruger, "Evaluation of key frame-based retrieval techniques for video," Computer Vision and Image Understanding, vol. 92, pp. 217-235, 2003.
[7] M. J. Pickering, D. Heesch, R. O'Callaghan, S. Ruger, and D. Bull, "Video retrieval using global features in keyframes," in Proc. of 11th Text Retrieval Conf., 2002.
[8] C. Y. Low, H. J. Zhang, and S. W. Smoliar, "Video parsing, retrieval and browsing: An integrated and content-based solution," in Proc. of the ACM Int. Conf. on Multimedia, pp. 15-24, 1995.
[9] M. R. Naphade, T. Kristjansson, B. Frey, and T. S. Huang, "Probabilistic multimedia objects (multijects): A novel approach to video indexing and retrieval in multimedia systems," in Proc. of Int. Conf. on Image Processing, vol. 3, pp. 536-540, 1998.
[10] T. S. Chua and L. Q. Ruan, "A video retrieval and sequencing system," ACM Transactions on Information Systems, vol. 13, pp. 373-407, 1995.
[11] R. Qian, N. Haering, and I. Sezan, "A computational approach to semantic event detection," IEEE Trans. on Computer Vision and Pattern Recongnition, vol. 1, pp. 200-206, 1999.
[12] A. Hampapur, R. Jain, and T. Weymouth, "Digital video segmentation," in Proc. of the ACM Int. Conf. on Multimedia, pp. 357-364, 1994.
[13] T. Volkmer, S. M. M. Tahaghoghi, and H. E. Williams, "Gradual transition detection using avgerage frame similarity," in Proc. of Int. Conf. on Computer Vision and Pattern Recognition Workshop, pp. 139-147, 2004.
[14] D. Li, "Lighting change problem in shot detection," in Proc. of the 7th IEEE Int. Conf. on Electronics, Circuits and Systems, 2000.
[15] K. Tsui L. Gu and D. Keightley, "Dissolve detection in mpeg compressed video," in Proc. of IEEE Int. Conf. on Intelligent Processing, 1997.
[16] L. Tong and P. N. Suganthan, "An adaptive cumulation algorithm for video shot detection," in Proc. of 2001 Int. Sym. on Intelligent Multimedia, Video and Speech Processing, pp. 296-299, 2001.
[17] Z. Cernekova, C. Nikou, and I. Pitas, "Shot detection in video sequences using entropy based metrics," in Proc. of 2002 Int. Conf. on Image Processing, vol. 3, pp. III-421-424, 2002.
[18] Y. Yuan, Q. B. Song, and J. Y. Shen, "Automatic video classification using decision tree method," in Proc. of the First Int. Conf. on Machine Learning and Cybernetics, pp. 1153-1157, 2002.
[19] B. Jahne, Spatio-tmporal Image Processing: Theory and Scientific Applications., New York: Springer-Verlag, 1991.
[20] Pacific Cinematheque, "Lighting in filmmaking," Available:http://www.inpoint.org/.
[21] T. Hastie, R. Tibshirani, and J. Friedman, "The elements of statisticallearning, data mining, inference, and prediction," pp. 266-272, 2001.
[22] J. R. Quinlan, "C4.5: Programs for machine learning," 1993.
[23]"truemovie," Static from: http://www.truemovie.com/.
[24] U. Gargi, S. Oswald, D. Kosiba, S. Devadiga, and R. Kasturi, "Evaluation of video sequence indexing and hierarchical video index," in Proc. of SPIE Conf. on Storage and Retrieval in Image and Video Database, pp. 1522-1530, 1995.
[25] P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Tran. on Pattern Analysis and Machine Intelligence, vol. 12, pp. 629-639, 1990.
[26] G. Lupatini, C. Saraceno, and R. Leonardi, "Scene break detection: A comparison," in Proc. of the 8th Int. Workgroup, Research Issue in Data Engineer, 1998.
[27] S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice Hall, 1999.